理论 · online learning论文趋势 2023–2026

学习理论及相关：online_learning

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 763 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

理论 · online learning论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202310117397164
202416913348224
20258918744185
20266827869190

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部理论 · online learning论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 763 篇，第 6 / 16 页

  1. ICML 2025Near Optimal Non-asymptotic Sample Complexity of 1-Identification
  2. ICML 2025Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
  3. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
  4. ICML 2025Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
  5. ICML 2025Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
  6. ICML 2025Offline Learning for Combinatorial Multi-armed Bandits
  7. ICML 2025On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
  8. ICML 2025Online Clustering of Dueling Bandits
  9. ICML 2025Online Conformal Prediction via Online Optimization
  10. ICML 2025Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting
  11. ICML 2025Online Episodic Convex Reinforcement Learning
  12. ICML 2025Online Laplacian-Based Representation Learning in Reinforcement Learning
  13. ICML 2025Online Learning in Risk Sensitive constrained MDP
  14. ICML 2025Online Learning in the Random-Order Model
  15. ICML 2025Online Learning with Unknown Constraints
  16. ICML 2025Online Linear Classification with Massart Noise
  17. ICML 2025Online Pre-Training for Offline-to-Online Reinforcement Learning
  18. ICML 2025Online Sparsification of Bipartite-Like Clusters in Graphs
  19. ICML 2025Optimal Algorithm for Max-Min Fair Bandit
  20. ICML 2025Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
  21. ICML 2025Partially Observable Reinforcement Learning with Memory Traces
  22. ICML 2025Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity
  23. ICML 2025Revisiting Differentially Private Algorithms for Decentralized Online Learning
  24. ICML 2025Revisiting the Predictability of Performative, Social Events
  25. ICML 2025Reward-free World Models for Online Imitation Learning
  26. ICML 2025Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction
  27. ICML 2025Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
  28. ICML 2025Sleeping Reinforcement Learning
  29. ICML 2025Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
  30. ICML 2025Stochastic Online Conformal Prediction with Semi-Bandit Feedback
  31. ICML 2025The Batch Complexity of Bandit Pure Exploration
  32. ICML 2025The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
  33. ICML 2025Tracking Most Significant Shifts in Infinite-Armed Bandits
  34. ICML 2025Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
  35. ICML 2025Value-Based Deep RL Scales Predictably
  36. ICML 2025Zero-Inflated Bandits
  37. NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
  38. NeurIPS 2025Agnostic Continuous-Time Online Learning
  39. NeurIPS 2025An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
  40. NeurIPS 2025Asymptotic theory of SGD with a general learning-rate
  41. NeurIPS 2025Bandit and Delayed Feedback in Online Structured Prediction
  42. NeurIPS 2025Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
  43. NeurIPS 2025Computable universal online learning
  44. NeurIPS 2025Conformal Online Learning of Deep Koopman Linear Embeddings
  45. NeurIPS 2025Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning
  46. NeurIPS 2025Consistency of the $k_n$-nearest neighbor rule under adaptive sampling
  47. NeurIPS 2025Contextual Online Pricing with (Biased) Offline Data
  48. NeurIPS 2025Dynamic Regret Reduces to Kernelized Static Regret
  49. NeurIPS 2025Efficient Last-Iterate Convergence in Solving Extensive-Form Games
  50. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查理论 · online learning在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "theory-online-learning"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇理论 · online learning论文？
共 763 篇，按年份分别是 2023 年 164 篇、2024 年 224 篇、2025 年 185 篇、2026 年 190 篇。
NeurIPS 2026 有多少篇理论 · online learning论文？
NeurIPS 2026 有 68 篇理论 · online learning论文，上一届是 89 篇。
ICLR 2026 有多少篇理论 · online learning论文？
ICLR 2026 有 27 篇理论 · online learning论文，上一届是 18 篇。
ICML 2026 有多少篇理论 · online learning论文？
ICML 2026 有 86 篇理论 · online learning论文，上一届是 74 篇。
CVPR 2026 有多少篇理论 · online learning论文？
CVPR 2026 有 9 篇理论 · online learning论文，上一届是 4 篇。
哪个会议的理论 · online learning论文最多？
NeurIPS，2023–2026 年共 427 篇。

「理论与统计」下的其他主题